How Stanford Built a Humanoid Submarine Robot to Explore a 17th-Century Shipwreck

Exclusive photos take you through the first mission of Stanford’s diving robot

2 min read
Stanford's Ocean One is a hybrid between a humanoid robot and an underwater remotely operated vehicle.
Photo: Frederic Osada and Teddy Seguin/DRASSM/Stanford

Back in April, Stanford University professor Oussama Khatib led a team of researchers on an underwater archaeological expedition, 30 kilometers off the southern coast of France, to La Lune, King Louis XIV’s sunken 17th-century flagship. Rather than dive to the site of the wreck 100 meters below the surface, which is a very bad idea for almost everyone, Khatib’s team brought along a custom-made humanoid submarine robot called Ocean One.

In this month’s issue of IEEE Robotics and Automation Magazine, the Stanford researchers describe in detail how they designed and built the robot, a hybrid between a humanoid and an underwater remotely operated vehicle (ROV), and also how they managed to send it down to the resting place of La Lune, where it used its three-fingered hands to retrieve a vase.

Most ocean-ready ROVs are boxy little submarines that might have an arm on them if you’re lucky, but they’re not really designed for the kind of fine manipulation that underwater archaeology demands. You could send down a human diver instead, but once you get past about 40 meters, things start to get both complicated and dangerous. Ocean One’s humanoid design means that it’s easy and intuitive for a human to remotely perform delicate archeological tasks through a telepresence interface.

It’s an impressive and unique project (the full article is on IEEE Xplore) that demonstrates the possibilities of human-robot collaboration, and we agree with RAM editor-in-chief Bram Vanderborght when he says he’s “convinced that the complementary strengths of both humans and robots combined is the winning solution instead of simple human replacement.” We also agree with Bram that “the photos alone are brilliant,” so we teamed up with RAM to showcase some of them for you in the slideshow below. This is the beginning of a closer Spectrum-RAM collaboration so expect more slideshows, sneak peeks, and Q&As with authors next year. Enjoy!

Photo: Frederic Osada and Teddy Seguin/DRASSM/Stanford University

The researchers deploy their diving humanoid robot Ocean One in preparation for its mission to Louis XIV’s flagship.

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman
LightGreen

“I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

This article is part of our special report on AI, “The Great AI Reckoning.”

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓Show less